<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="susanto-etal-2019-sarahs">
    <titleInfo>
        <title>Sarah’s Participation in WAT 2019</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raymond</namePart>
        <namePart type="given">Hendy</namePart>
        <namePart type="family">Susanto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ohnmar</namePart>
        <namePart type="family">Htun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liling</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th Workshop on Asian Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes our MT systems’ participation in the of WAT 2019. We participated in the (i) Patent, (ii) Timely Disclosure, (iii) Newswire and (iv) Mixed-domain tasks. Our main focus is to explore how similar Transformer models perform on various tasks. We observed that for tasks with smaller datasets, our best model setup are shallower models with lesser number of attention heads. We investigated practical issues in NMT that often appear in production settings, such as coping with multilinguality and simplifying pre- and post-processing pipeline in deployment.</abstract>
    <identifier type="citekey">susanto-etal-2019-sarahs</identifier>
    <identifier type="doi">10.18653/v1/D19-5219</identifier>
    <location>
        <url>https://aclanthology.org/D19-5219</url>
    </location>
    <part>
        <date>2019-nov</date>
        <extent unit="page">
            <start>152</start>
            <end>158</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sarah’s Participation in WAT 2019
%A Susanto, Raymond Hendy
%A Htun, Ohnmar
%A Tan, Liling
%S Proceedings of the 6th Workshop on Asian Translation
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F susanto-etal-2019-sarahs
%X This paper describes our MT systems’ participation in the of WAT 2019. We participated in the (i) Patent, (ii) Timely Disclosure, (iii) Newswire and (iv) Mixed-domain tasks. Our main focus is to explore how similar Transformer models perform on various tasks. We observed that for tasks with smaller datasets, our best model setup are shallower models with lesser number of attention heads. We investigated practical issues in NMT that often appear in production settings, such as coping with multilinguality and simplifying pre- and post-processing pipeline in deployment.
%R 10.18653/v1/D19-5219
%U https://aclanthology.org/D19-5219
%U https://doi.org/10.18653/v1/D19-5219
%P 152-158

Markdown (Informal)

[Sarah’s Participation in WAT 2019](https://aclanthology.org/D19-5219) (Susanto et al., EMNLP 2019)

• Sarah’s Participation in WAT 2019 (Susanto et al., EMNLP 2019)

ACL

• Raymond Hendy Susanto, Ohnmar Htun, and Liling Tan. 2019. Sarah’s Participation in WAT 2019. In Proceedings of the 6th Workshop on Asian Translation, pages 152–158, Hong Kong, China. Association for Computational Linguistics.